BigData, Machine-learning, AI & AnalyticsBigData, Machine-learning, AI & Analytics
Deep Dive120min
INTERMEDIATE

Spring AI Deep Dive: Building Production-Ready Agentic Applications

This session offers a practical deep dive into Spring AI for Java developers, covering architecture, memory and tool integration, authentication, observability, deployment, scalability, and testing of non‑deterministic behavior. Attendees learn concrete patterns to build, secure, monitor, and scale reliable, production‑ready agentic AI systems using Spring AI.

talk.summaryAiDisclaimer

Andrei Shakirin
Andrei ShakirinAmazon Web Services
Laura Schlosser
Laura SchlosserAmazon Web Services
talks.description
Spring AI enables Java and Spring developers to design and implement production-ready Agentic AI systems using a familiar programming model. In this 120-minute deep dive, we explore the most powerful capabilities of the Spring AI framework — evolving from a simple chat application to a secure, observable, and scalable agentic system.
The session covers:
  • Architecting AI-driven Spring applications using maintainable and consistent design patterns
  • Integrating memory and external tools, including MCP client and server implementations
  • Securing AI workflows with proper authentication and authorization, including secure MCP tool calls
  • Applying observability and monitoring to AI-driven features
  • Evaluating deployment and scalability strategies
  • Testing non-deterministic AI behavior, from slice tests to system and load testing
  • Implementing advanced agentic patterns such as Tool Search Tool, Agent Skills, and capturing LLM reasoning for traceability and control
Participants will gain a comprehensive understanding of Spring AI in real-world scenarios, along with concrete patterns for designing, testing, securing, and operating AI-enabled applications. This session is ideal for Java and Spring engineers seeking a deep, practical exploration of reliable, secure, and maintainable agentic systems.
agentic
security
springai
observability
talks.speakers
Andrei Shakirin

Andrei Shakirin

Amazon Web Services

Germany

Andrei is a Solutions Architect at Amazon Web Services and a former Pivotal Labs engineer, specializing in the design of highly scalable systems and generative AI applications. He is an active committer to several Spring and Apache open-source projects, contributor into MCP java SDK and a regular speaker at technical conferences. His areas of interest include Java and Spring, GenAI integration, MCP, resilient distributed systems, security, and domain-driven design.
Laura Schlosser

Laura Schlosser

Amazon Web Services

Germany

Solutions Architect at AWS by day, Java developer at heart, always. From Romania to Germany, from code to architecture, one thing stayed constant: turning complexity into clarity.

I taught my first Java courses as a volunteer in Romania, just to give back. That led to 7+ years writing software, leading international teams, and eventually joining AWS as a Solutions Architect. After stepping away to raise my kids, right before generative AI exploded onto the scene, I came back to find a whole new world: AI had changed everything. Back now, and obsessed with one question: how do we bring AI into the Java world?